PK
}XGM M $
WPO-20160329204309-crawl893_meta.xmlUT
f
f
WPO-20160329204309-crawl893
http://archive.org/details/WPO-20160329204309-crawl893
Internet Archive
Heritrix/3.1.2-SNAPSHOT-20130614-1356
wikipedia
Internet Archive
2016
Internet Archive crawldata from Wikipedia Outlinks Crawl, captured by crawl893.us.archive.org:wikipedia from Tue Mar 29 20:43:09 PDT 2016 to Tue Mar 29 13:59:57 PDT 2016.
20160329204016
05879
20160329135957
20160329205839
05881
web
3
lekash@archive.org
20160329204016
crawl893.us.archive.org
sanfrancisco
7455307841
Internet Archive
crawldata
Wikipedia Outlinks Crawldata 2016-03-29T20:43:09PDT to 2016-03-29T13:59:57PDT
wikipediaoutlinks00004
wikipediaoutlinks
wikicollections
web
2016-03-30 12:00:09
lekash@archive.org
2016-03-30 12:00:09
24757
ia906103_17
PK
}XZ , , '
WPO-20160329204309-crawl893_meta.sqliteUT
f
fSQLite format 3 @ , , -
H {H 1 M
WPO-20160329205618-05881.warc.gzputAվ1 M
WPO-20160329205009-05880.warc.gzputAվo1 M
WPO-20160329204309-05879.warc.gzputAվUX %
MANIFEST.txtputAվ
g g M]
WPO-20160329205618-05881.warc.gzETag: "6dc389252d90aabf990b5b5ddffbd7ab"
accept: */*
authorization: LOW cXmrjHI8KPpgaeD9:REDACTED_BY_IA_S3
connection: close
content-length: 1066824970
content-md5: 6dc389252d90aabf990b5b5ddffbd7ab
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-ias3-encoded-key: WPO-20160329205618-05881.warc.gz
x-upload-date: 2016-03-30T12:11:26.000Z
AվP
I I ,%1
MANIFEST.txtETag: "a09437945fdc87d86301a7e3c91efd17"
accept: */*
authorization: LOW cXmrjHI8KPpgaeD9:REDACTED_BY_IA_S3
connection: close
content-length: 201
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-amz-auto-make-bucket: 1
x-archive-meta-access: http://archive.org/details/WPO-20160329204309-crawl893
x-archive-meta-contributor: Internet Archive
x-archive-meta-crawler: Heritrix/3.1.2-SNAPSHOT-20130614-1356
x-archive-meta-crawljob: wikipedia
x-archive-meta-creator: Internet Archive
x-archive-meta-date: 2016
x-archive-meta-description: Internet Archive crawldata from Wikipedia Outlinks Crawl, captured by crawl893.us.archive.org:wikipedia from Tue Ma
$MWPO-20160329205618-05881.warc.gz$MWPO-20160329205009-05880.warc.gz$MWPO-20160329204309-05879.warc.gz% MANIFEST.txt
H Hpu %99etables3item_pending_changess3item_pending_changesCREATE TABLE s3item_pending_changes
(
sequence_number INTEGER PRIMARY KEY ASC,
op blob,
args blob,
time float,
done int default 0
)))?tables3item_historys3item_historyCREATE TABLE s3item_history
(
sequence_number INTEGER PRIMARY KEY ASC,
key blob,
op blob,
data blob,
time float
);99tables3api_per_key_metadatas3api_per_key_metadataCREATE TABLE s3api_per_key_metadata
(
s3key blob,
headers blob,
live_date real,
old_version_of blob,
primary key (s3key),
unique (s3key)
)K_9 indexsqlite_autoindex_s3api_per_key_metadata_1s3api_per_key_metadata r 29 20:43:09 PDT 2016 to Tue Mar 29 13:59:57 PDT 2016.
x-archive-meta-firstfiledate: 20160329204309
x-archive-meta-firstfileserial: 05879
x-archive-meta-lastdate: 20160329135957
x-archive-meta-lastfiledate: 20160329205618
x-archive-meta-lastfileserial: 05881
x-archive-meta-mediatype: web
x-archive-meta-numwarcs: 3
x-archive-meta-operator: lekash@archive.org
x-archive-meta-scandate: 20160329204309
x-archive-meta-scanner: crawl893.us.archive.org
x-archive-meta-scanningcenter: sanfrancisco
x-archive-meta-sizehint: 7455307841
x-archive-meta-sponsor: Internet Archive
x-archive-meta-subject: crawldata
x-archive-meta-title: Wikipedia Outlinks Crawldata 2016-03-29T20:43:09PDT to 2016-03-29T13:59:57PDT
x-archive-meta01-collection: wikipediaoutlinks00004
x-archive-meta02-collection: wikipediaoutlinks
x-archive-meta03-collection: wikicollections
x-archive-meta04-collection: web
x-archive-queue-derive: 0
x-archive-size-hint: 7455307841
x-ias3-encoded-key: MANIFEST.txt
x-upload-date: 2016-03-30T12:00:08.000Z
Aվ@!
M 0M
WPO-20160329205009-05880.warc.gzETag: "ff215185a912d2c57449e901e844ad6f"
accept: */*
authorization: LOW cXmrjHI8KPpgaeD9:REDACTED_BY_IA_S3
connection: close
content-length: 3313019523
content-md5: ff215185a912d2c57449e901e844ad6f
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: WPO-20160329205009-05880.warc.gz
x-upload-date: 2016-03-30T12:10:52.000Z
AվZ0M
WPO-20160329204309-05879.warc.gzETag: "f0d165423797a3940e03fcfe7c118cfe"
accept: */*
authorization: LOW cXmrjHI8KPpgaeD9:REDACTED_BY_IA_S3
connection: close
content-length: 3075463348
content-md5: f0d165423797a3940e03fcfe7c118cfe
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: WPO-20160329204309-05879.warc.gz
x-upload-date: 2016-03-30T12:05:11.000Z
AվT?PK
}Xʚ %
WPO-20160329204309-crawl893_files.xmlUT
f
f
1459339208
201
a09437945fdc87d86301a7e3c91efd17
209d21ec
d722beb2ddf8a0753fc71da2ad93af2238ebf965
Text
true
1459339510
3075463348
f0d165423797a3940e03fcfe7c118cfe
41c1ef2b
a7476008fd389b94b70bf34af83a353f05d85924
Web ARChive GZ
true
WARC CDX Index
WPO-20160329204309-05879.warc.gz
1459341243
1204164
efea9308ab18b80ad25b4d76bbba84d2
2d3dfbee
bce9faf7d405c939d6dca08ba065501dae756dfd
true
1459341374
1989792
60d25662259714e976a537d78e69fef9
a6ddaaee
a491e717e92dbb5c5c8df12b86d288cf004a6075
Item CDX Index
true
1459341374
966
b37e3580178c3820e7b0d1bc967d3996
8e6fcdbf
0098f36cf537a845a42af49fefd5429295c8618e
Item CDX Meta-Index
true
Metadata
a1c941e67fd02ecb55e59d5fc4c2d32f
md5
1459340384
11264
Metadata
8699e83ca83c478e507a7da6f761a691
fd5ad7ce
557bd97558303a88054af04f82b0df62d633cfa1
1484112999
1613
Metadata
794025223a1056260d82c669ec4a5270
97471287
d5d042e648441745adec7d9946b159f9e4196113
1459339852
3313019523
ff215185a912d2c57449e901e844ad6f
07d791ea
c291e23532357df1daad1c0c3d463ed020e31b3c
Web ARChive GZ
true
WARC CDX Index
WPO-20160329205009-05880.warc.gz
1459341296
37954
a52d1b29700b511fd5347321ece94329
f57cdc47
d86a95e268842b7d833d292cbeaacd733455c4a9
true
1459339886
1066824970
6dc389252d90aabf990b5b5ddffbd7ab
c6cfd3a8
f779be9fe353a02b37162df5d79311c22d9aff6b
Web ARChive GZ
true
WARC CDX Index
WPO-20160329205618-05881.warc.gz
1459341335
881357
1683b206d9deb37f6a0d232918277ef8
888cda04
b18d9507c9d4113f6a97798c2be9312366cec003
true
PK-
}XGM M $ @ WPO-20160329204309-crawl893_meta.xmlUT
fPK-
}XZ , , ' @ WPO-20160329204309-crawl893_meta.sqliteUT
fPK-
}Xʚ % @2 WPO-20160329204309-crawl893_files.xmlUT
fPK B